<![CDATA[This study examines the use of predictive analytics for the early detection of depression among teenagers based on social media usage patterns and behavioral indicators. The research utilizes a secondary dataset consisting of 1,200 adolescent records, including variables such as daily social media usage duration, sleep duration, stress level, anxiety level, addiction tendency, academic performance, physical activity, and depression classification labels. A quantitative approach was applied using machine learning algorithms, including Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine. The dataset was processed through data cleaning, encoding, normalization, exploratory data analysis, feature selection, model development, and model evaluation. The results show that sleep duration, daily social media usage, stress level, anxiety level, and academic performance are important predictors of teen depression.]]>
Copyrights © 2026
